AI Red Team Specialist – Lead Researcher in Agentic Security
The Tech Collective · Copenhagen, Capital Region of Denmark, Denmark
- On site
- Full-time
- $150,000 / year
- Copenhagen, Capital Region of Denmark, Denmark
Job highlights
- Develop LLM testing and evaluation tools.
- Collaborate with diverse security experts.
- Focus on agentic security vulnerabilities.
- Opportunity for research and development.
- Hybrid work model with remote flexibility.
About the role
AI Red Team Specialist – Lead Researcher in Agentic Security
The Tech Collective is seeking an experienced red teamer with proven credentials in agentic red teaming to join our advanced product and research team.
What You’ll Do
- Join the team dedicated to building and developing a tool that dynamically tests and evaluates large language models (LLMs) and their native application context for vulnerabilities.
- Work with seasoned reverse engineers, application pentesters, red teamers, and data scientists, bridging multiple digital disciplines.
- Create a unique suite that gives clients the capability to test, remediate, and harden their agentic workloads.
What You’ll Bring
We value ingenuity, curiosity, and drive. You may be a great fit for this role if you have experience with:
- Building or contributing to tools used for dynamic application testing.
- Working extensively with open source or proprietary tools for web and application pentesting.
- Actively adopting LLMs and Model Context Protocol (MCP) to automate and enhance penetration tests.
- Researching agentic vulnerabilities and attending relevant trainings or conferences.
To Fit Right In Here At The Tech Collective
- Be genuinely curious about new developments within the red teaming domain.
- Possess the willingness to tackle new and technical challenges.
- Know how to break down and structure complex assignments and enjoy sharing knowledge.
- Have a startup mentality to drive innovation and ingenuity of our red team products.
- Cooperate seamlessly with diverse teams of researchers, developers, consultants, and red teamers.
We are looking for someone who wants to own, develop, and innovate product modules related to testing application context (e.g., API security, cryptographic implementation, broken authentication, RBAC) and supporting infrastructure (e.g., misconfigurations, server-side vulnerabilities) for agents.
Experience and Competencies Should Include:
Professional experience
- A minimum of five years’ progressive experience in enterprise red teaming or offensive research.
- A proven track record of web application pentesting with an emphasis on remediation and hardening.
- Experience defining and driving product roadmaps for red team tools (highly valued).
- Demonstrated ability to evaluate complex technology stacks, including common cloud platforms (M365/Azure, Google, or AWS), CI/CD pipelines, and AI-powered platforms and systems.
- Experience communicating technical findings to non-technical stakeholders.
Technical competencies
- Familiarity with both Mitre and OWASP frameworks, and experience applying them in client reporting.
- Relevant security certifications (e.g., OSCP, OSCE, OSEP, GIAC GPEN/GXPN) are a plus.
- Prior experience developing agent-specific attack types such as prompt injection, memory & context poisoning, or jailbreaking.
- A working understanding of MCP, LLM pipelines, LLM functional aspects, and how modern agent solutions integrate with cloud suites like M365 or AWS.
Experience in intermediate to advanced vulnerability research related to applications or operating systems will be a strong plus.
What we offer
- Competitive salary and bonus package.
- Opportunity to join a unique team of experts and enthusiasts.
- Investment in your development through training, conferences, or research opportunities.
- Combination of remote work with meaningful co-working at our offices in Copenhagen.
- Tooling and hardware required to build a unique red team platform.
For questions or enquiries, feel free to contact Anders Rømer Skøtt at anrs@thetechcollective.eu // +45 31717487.
Key skills/competency
- AI Red Team Specialist
- Agentic Security
- Large Language Models (LLMs)
- Penetration Testing
- Vulnerability Research
- Reverse Engineering
- Offensive Security
- Cloud Security
- Product Development
- Risk Management
Skills & topics
- AI Red Team Specialist
- Agentic Security
- LLM Security
- Penetration Testing
- Vulnerability Research
- Offensive Security
- Cybersecurity
- Red Teaming
- Application Security
- Cloud Security
How to get hired
- Tailor your resume: Highlight your experience with agentic security, LLMs, and penetration testing tools. Quantify achievements in red teaming and vulnerability research.
- Showcase your expertise: Emphasize your research, tool development contributions, and any relevant security certifications in your application.
- Demonstrate curiosity: Prepare to discuss your passion for new developments in red teaming and your willingness to tackle complex challenges.
- Prepare for technical interviews: Be ready to discuss specific attack types (prompt injection, jailbreaking) and your understanding of MCP and LLM pipelines.
- Network and inquire: Reach out to Anders Rømer Skøtt at anrs@thetechcollective.eu with specific questions about the AI Red Team Specialist role.
Technical preparation
Master prompt injection and jailbreaking techniques.,Deep dive into MCP and LLM pipelines.,Practice dynamic application testing tools.,Familiarize with cloud security configurations.
Behavioral questions
How do you approach complex security challenges?,Describe a time you drove product innovation.,How do you share technical knowledge with others?,How do you adapt to rapidly evolving fields?
Frequently asked questions
- What specific experience does The Tech Collective seek for the AI Red Team Specialist role?
- The Tech Collective is looking for an AI Red Team Specialist with a minimum of five years' experience in enterprise red teaming or offensive research. Key areas include web application pentesting, developing agent-specific attack types like prompt injection, and a strong understanding of LLMs and Model Context Protocol (MCP). Experience in tool development for dynamic testing and communicating technical findings is also crucial.
- How does The Tech Collective support the professional development of its AI Red Team Specialist?
- The Tech Collective invests in employee development through competitive salaries, bonuses, and opportunities for training, conferences, and pursuing independent research in passionate areas. They also provide the necessary tooling and hardware to foster innovation in red team platforms.
- What is the work arrangement for the AI Red Team Specialist position at The Tech Collective?
- The AI Red Team Specialist role combines remote work with meaningful co-working at their Copenhagen offices, offering a hybrid work arrangement. This allows for flexibility while maintaining team collaboration.
- What technical competencies are most important for an AI Red Team Specialist at The Tech Collective?
- Key technical competencies include familiarity with Mitre and OWASP frameworks, experience with agent-specific attacks (prompt injection, jailbreaking), and a working understanding of MCP, LLM pipelines, and their integration with cloud platforms like AWS or M365. While not strictly required, relevant security certifications are a plus.
- How can I best prepare my application for the AI Red Team Specialist role at The Tech Collective?
- To best prepare your application, highlight your experience in agentic security, LLM vulnerability research, and dynamic application testing. Quantify your achievements, showcase any tool development contributions, and demonstrate your genuine curiosity and willingness to tackle complex challenges in the rapidly evolving field of AI security.
- What kind of team will an AI Red Team Specialist join at The Tech Collective?
- An AI Red Team Specialist will join an advanced product and research team comprised of seasoned reverse engineers, application pentesters, red teamers, and data scientists. It's a diverse team focused on innovation and developing cutting-edge tools for agentic security.
- What are the core responsibilities of the AI Red Team Specialist role?
- The core responsibilities include building and developing tools to dynamically test and evaluate LLMs and their application context for vulnerabilities. This involves researching agentic vulnerabilities and owning product modules for testing agent application context and supporting infrastructure.